Projects sharing features with Bert Score

ColBERT is a neural information retrieval model and dense passage retrieval framework. It functions as a search engine that uses contextual embeddings to index text passages and retrieve relevant documents based on semantic meaning rather than keyword matching. The system is distinguished by a late interaction architecture that defers the calculation of query and document similarity until the final step. It employs multi-vector indexing to store separate embeddings for every token in a document, enabling granular matching against query terms. The project covers document indexing, passage ret

Flair is a transformer-based natural language processing framework used to build and train models for text classification and sequence tagging. It provides a specialized library for generating contextual text embeddings and performing linguistic analysis. The framework includes dedicated tools for named entity recognition, including the identification of specialized biomedical entities across multiple languages. It further supports entity linking to map identified text mentions to unique entries within general or biomedical knowledge bases. The project covers a broad range of language analys

This project is a self-hosted system for discovering, browsing, and receiving personalized recommendations from academic papers on arXiv. It combines an arXiv API client that downloads paper metadata and PDFs with a TF-IDF document similarity engine and an SVM-based recommendation system that trains a classifier per user based on their preferences. The system provides a web interface for browsing, searching, and filtering recent arXiv submissions, alongside personalized paper recommendations generated from individual user signals. It also includes a Twitter mention tracker that periodically p

Fuzzywuzzy is a Python library and text processing utility designed to calculate similarity scores between strings. It functions as a text similarity scoring engine and an approximate string matching tool used to identify the closest textual matches within a list of candidate strings. The library provides a suite of tools for measuring the degree of similarity between pieces of text, accounting for typos and formatting differences. These capabilities include extracting the best match from a candidate list and performing fuzzy string matching through various scoring methods. The toolset cover

RapidFuzz is a C++ accelerated Python library providing high-performance string comparison and similarity calculations. It functions as a fuzzy string matching toolkit used to quantify the difference between text sequences through Levenshtein distance and other edit distance metrics. The library focuses on scalable approximate text matching, enabling the identification and ranking of similar strings within large datasets. It provides specialized utilities for finding the best matches in a collection and generating pairwise similarity matrices. The project covers a broad surface of text proce

This project is a training pipeline and framework for developing Chinese language models based on the Llama 2 architecture. It functions as a distributed GPU trainer and dataset preprocessing toolkit designed for both the initial pre-training of baseline models and subsequent supervised fine-tuning. The system distinguishes itself through a specialized workflow for Chinese text, incorporating a data curation pipeline that uses similarity hashing for deduplication and a tokenization process that converts raw text into memory-mapped binary files for efficient disk access. It implements a superv

This project is a comprehensive resource directory for web data extraction, providing a curated collection of tools and libraries for parsing data, automating browsers, and managing network operations. It serves as a guide for extracting structured information from HTML, XML, JSON, and PDF formats. The toolkit focuses on advanced data collection strategies, including headless browser automation to interact with JavaScript and a suite of network utilities for DNS resolution and WebSocket connections. It specifically covers methods for bypassing bot protections through proxy pool management, us

nlp-recipes is a collection of implementation guides and reference templates for applying natural language processing techniques to real-world tasks. It provides standardized workflows and code examples for developing NLP pipelines, from dataset preparation and model training to performance evaluation. The project focuses on the practical application of transformer-based models, offering patterns for fine-tuning pretrained architectures for tasks such as text classification, named entity recognition, and question answering. It also includes a toolkit for model interpretability, allowing users

SnowNLP is a Python library for Chinese natural language processing. It provides tools for text segmentation, sentiment analysis, document classification, and phonetic transliteration. The library includes capabilities for training and saving custom machine learning models for tokenization and sentiment analysis using raw training datasets. It covers a range of linguistic processing areas, including parts of speech tagging, sentence splitting, and text similarity measurement. The toolkit also provides utilities for extracting key information through text summarization and calculating word im

This project provides a self-hosted server for automatic speech recognition, functioning as a containerized inference engine for the Whisper model. It exposes core transcription and translation capabilities through a standardized web interface, allowing for the integration of speech-to-text services into external applications. The service distinguishes itself by incorporating advanced audio analysis tools, including speaker diarization to attribute text to specific individuals and voice activity detection to filter non-speech segments. It supports automated language detection and provides out

KServe is a Kubernetes-native platform for deploying and serving machine learning models as scalable inference services. It supports both generative AI models, including large language models, and traditional predictive models from frameworks such as TensorFlow, PyTorch, Scikit-Learn, XGBoost, and ONNX. The platform manages the full lifecycle of model deployments, including revision tracking, canary rollouts, A/B testing, and automatic rollbacks, and provides serverless scale-to-zero capabilities for cost-efficient resource management. KServe distinguishes itself through a standardized infere

KServe is an open platform for deploying and serving generative and predictive AI models on Kubernetes. It defines inference services as custom resources with declarative YAML specifications, enabling a Kubernetes-native approach to model deployment and lifecycle management. The platform leverages Knative-based serverless scaling for automatic scale-to-zero and revision management, and supports a pluggable serving runtime architecture that maps model formats to containerized execution environments. KServe distinguishes itself through model-aware autoscaling that scales replicas based on token

ComfyUI-SeedVR2_VideoUpscaler is an AI video upscaling tool that uses diffusion models to increase the resolution of videos and images while maintaining visual consistency across frames. The project implements distributed video rendering by splitting datasets into chunks for parallel processing across multiple GPUs. It utilizes model compilation and specialized attention backends to reduce inference latency and increase throughput. Additional capabilities include video color correction using wavelet and LAB matching methods to preserve color fidelity. Hardware memory is managed through block

Pocket-tts is a text-to-speech server and neural speech synthesizer that converts written text into audible speech. It includes a CPU-optimized inference engine and a voice cloning tool capable of analyzing audio samples to reproduce specific speaker characteristics. The system differentiates itself through the use of dynamic int8 quantization to reduce memory usage and increase generation speed on processors. It supports real-time speech synthesis by streaming audio chunks incrementally and utilizes voice state caching to store processed embeddings as portable files, bypassing redundant proc

AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc